English
Related papers

Related papers: Controllable and Verifiable Tool-Use Data Synthesi…

200 papers

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be…

Machine Learning · Computer Science 2026-03-17 Mumuksh Tayal , Manan Tayal , Ravi Prakash

Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods…

Machine Learning · Computer Science 2025-03-18 Kun Wu , Yinuo Zhao , Zhiyuan Xu , Zhengping Che , Chengxiang Yin , Chi Harold Liu , Feiferi Feng , Jian Tang

Offline reinforcement learning (RL) has increasingly become the focus of the artificial intelligent research due to its wide real-world applications where the collection of data may be difficult, time-consuming, or costly. In this paper, we…

Machine Learning · Computer Science 2021-05-13 Chenyang Xi , Bo Tang , Jiajun Shen , Xinfu Liu , Feiyu Xiong , Xueying Li

Reinforcement learning has been shown to improve the performance of large language models. However, traditional approaches like RLHF or RLAIF treat the problem as single-step. As focus shifts toward more complex reasoning and agentic tasks,…

Artificial Intelligence · Computer Science 2025-04-29 Anna Goldie , Azalia Mirhoseini , Hao Zhou , Irene Cai , Christopher D. Manning

Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the…

Systems and Control · Electrical Eng. & Systems 2025-07-31 Alex Durkin , Jasper Stolte , Matthew Jones , Raghuraman Pitchumani , Bei Li , Christian Michler , Mehmet Mercangöz

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…

Machine Learning · Computer Science 2026-02-04 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this paper, we present…

Robotics · Computer Science 2024-07-11 Younggyo Seo , Jafar Uruç , Stephen James

Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajectory sampled from a prompt to termination, including…

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

Computation and Language · Computer Science 2025-12-15 Mrinal Rawat , Arkajyoti Chakraborty , Neha Gupta , Roberto Pieraccini

Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on…

Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while unconstrained RFT achieves strong reasoning performance, it…

Machine Learning · Computer Science 2026-02-03 Shuozhe Li , Jincheng Cao , Bodun Hu , Aryan Mokhtari , Leqi Liu , Amy Zhang

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

Machine Learning · Computer Science 2025-09-04 Sherry Yang , Joy He-Yueya , Percy Liang

Safe reinforcement learning (RL) with hard constraint guarantees is a promising optimal control direction for multi-energy management systems. It only requires the environment-specific constraint functions itself a priori and not a complete…

Systems and Control · Electrical Eng. & Systems 2023-11-07 Glenn Ceusters , Muhammad Andy Putratama , Rüdiger Franke , Ann Nowé , Maarten Messagie

Vision-Language Models (VLMs) struggle with complex image annotation tasks, such as emotion classification and context-driven object detection, which demand sophisticated reasoning. Standard Supervised Fine-Tuning (SFT) focuses solely on…

Machine Learning · Computer Science 2025-09-16 Suhang Hu , Wei Hu , Yuhang Su , Fan Zhang

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it…

Machine Learning · Computer Science 2021-04-27 Ashvin Nair , Abhishek Gupta , Murtaza Dalal , Sergey Levine

Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment remains challenging: existing reinforcement learning approaches rely on coarse…

Artificial Intelligence · Computer Science 2026-03-12 Pengbo Liu

Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, primarily in two forms: (1) input-output (I/O) prediction…

Software Engineering · Computer Science 2026-03-13 Lingxiao Tang , He Ye , Zhaoyang Chu , Muyang Ye , Zhongxin Liu , Xiaoxue Ren , Lingfeng Bao

Although the power of LLM tool-use agents has ignited a flurry of recent research in this area, the curation of tool-use training data remains an open problem$-$especially for online RL training. Existing approaches to synthetic tool-use…

Machine Learning · Computer Science 2025-09-25 Michael Sullivan , Mareike Hartmann , Alexander Koller

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

Systems and Control · Electrical Eng. & Systems 2020-09-29 Milad Kazemi , Sadegh Soudjani

Recent advances in Reinforcement Learning with Verified Reward (RLVR) have driven the emergence of more sophisticated cognitive behaviors in large language models (LLMs), thereby enhancing their reasoning capabilities. However, in prior…

Machine Learning · Computer Science 2025-08-26 Qingbin Li , Rongkun Xue , Jie Wang , Ming Zhou , Zhi Li , Xiaofeng Ji , Yongqi Wang , Miao Liu , Zheming Yang , Minghui Qiu , Jing Yang